Fast Bridgeless Pyramid Segmentation for Organized Point Clouds

MADARAS, Martin, Martin STUCHLIK and Matúš TALČÍK. Fast Bridgeless Pyramid Segmentation for Organized Point Clouds. Online. In Farinella, GM Radeva, P Braz, J Bouatouch, K. VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 4: VISAPP. SETUBAL: SCITEPRESS, 2021, p. 205-210. ISBN 978-989-758-488-6. Available from: https://dx.doi.org/10.5220/0010163802050210.

Basic information

• Original name: Fast Bridgeless Pyramid Segmentation for Organized Point Clouds
• Authors: MADARAS, Martin, Martin STUCHLIK and Matúš TALČÍK (703 Slovakia, belonging to the institution).
• Edition: SETUBAL, VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 4: VISAPP, p. 205-210, 6 pp. 2021.
• Publisher: SCITEPRESS

Other information

• Original language: English
• Type of outcome: Proceedings paper
• Field of Study: 10201 Computer sciences, information science, bioinformatics
• Country of publisher: Portugal
• Confidentiality degree: is not subject to a state or trade secret
• Publication form: electronic version available online
• RIV identification code: RIV/00216224:14330/21:00123673
• Organization unit: Faculty of Informatics
• ISBN: 978-989-758-488-6
• Doi: http://dx.doi.org/10.5220/0010163802050210
• UT WoS: 000668577400019
• Keywords in English: Point Cloud; Segmentation; Parallel; Pyramid; GPU; CUDA
• Tags: firank_B
• Tags: International impact, Reviewed

Abstract

An intelligent automatic robotic system needs to understand the world as fast as possible. A common way to capture the world is to use a depth camera. The depth camera produces an organized point cloud that later needs to be processed to understand the scene. Usually, segmentation is one of the first preprocessing steps for the data processing pipeline. Our proposed pyramid segmentation is a simple, fast and lightweight split-and-merge method designed for depth cameras. The algorithm consists of two steps, edge detection and a hierarchical method for bridgeless labeling of connected components. The pyramid segmentation generates the seeds hierarchically, in a top-down manner, from the largest regions to the smallest ones. The neighboring areas around the seeds are filled in a parallel manner, by rendering axis-aligned line primitives, which makes the performance of the method fast. The hierarchical approach of labeling enables to connect neighboring segments without unnecessary bridges in a parallel way that can be efficiently implemented using CUDA.